Learning Centre

The Effect of Different Flaw Data to Machine Learning Powered Ultrasonic Inspection

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Koskinen, Tuomas
dc.contributor.author Virkkunen, Iikka
dc.contributor.author Siljama, Oskar
dc.contributor.author Jessen-Juhler, Oskari
dc.date.accessioned 2021-03-22T07:13:54Z
dc.date.available 2021-03-22T07:13:54Z
dc.date.issued 2021-03
dc.identifier.citation Koskinen , T , Virkkunen , I , Siljama , O & Jessen-Juhler , O 2021 , ' The Effect of Different Flaw Data to Machine Learning Powered Ultrasonic Inspection ' , Journal of Nondestructive Evaluation , vol. 40 , no. 1 , 24 . https://doi.org/10.1007/s10921-021-00757-x en
dc.identifier.issn 0195-9298
dc.identifier.other PURE UUID: fdaa84d7-81c8-4b0d-b744-375daeedd24b
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/fdaa84d7-81c8-4b0d-b744-375daeedd24b
dc.identifier.other PURE LINK: http://www.scopus.com/inward/record.url?scp=85101141330&partnerID=8YFLogxK
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/56829941/Koskinen2021_Article_TheEffectOfDifferentFlawDataTo.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/103321
dc.description.abstract Previous research (Li et al., Understanding the disharmony between dropout and batch normalization by variance shift. CoRR abs/1801.05134 (2018). http://arxiv.org/abs/1801.05134arXiv:1801.05134) has shown the plausibility of using a modern deep convolutional neural network to detect flaws from phased-array ultrasonic data. This brings the repeatability and effectiveness of automated systems to complex ultrasonic signal evaluation, previously done exclusively by human inspectors. The major breakthrough was to use virtual flaws to generate ample flaw data for the teaching of the algorithm. This enabled the use of raw ultrasonic scan data for detection and to leverage some of the approaches used in machine learning for image recognition. Unlike traditional image recognition, training data for ultrasonic inspection is scarce. While virtual flaws allow us to broaden the data considerably, original flaws with proper flaw-size distribution are still required. This is of course the same for training human inspectors.The training of human inspectors is usually done with easily manufacturable flaws such as side-drilled holes and EDM notches. While the difference between these easily manufactured artificial flaws and real flaws is obvious, human inspectors still manage to train with them and perform well in real inspection scenarios. In the present work, we use a modern, deep convolutional neural network to detect flaws from phased-array ultrasonic data and compare the results achieved from different training data obtained from various artificial flaws. The model demonstrated good generalization capability toward flaw sizes larger than the original training data, and the effect of the minimum flaw size in the data set affects the a90 / 95 value. This work also demonstrates how different artificial flaws, solidification cracks, EDM notch and simple simulated flaws generalize differently. en
dc.format.extent 13
dc.format.mimetype application/pdf
dc.language.iso en en
dc.relation.ispartofseries Journal of Nondestructive Evaluation en
dc.relation.ispartofseries Volume 40, issue 1 en
dc.rights openAccess en
dc.title The Effect of Different Flaw Data to Machine Learning Powered Ultrasonic Inspection en
dc.type A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä fi
dc.description.version Peer reviewed en
dc.contributor.department Department of Mathematics and Systems Analysis
dc.contributor.department Advanced Manufacturing and Materials
dc.contributor.department Department of Mechanical Engineering
dc.contributor.department VTT Technical Research Centre of Finland
dc.subject.keyword Image classification
dc.subject.keyword Machine Learning
dc.subject.keyword NDT
dc.subject.keyword Ultrasonic testing
dc.identifier.urn URN:NBN:fi:aalto-202103222600
dc.identifier.doi 10.1007/s10921-021-00757-x
dc.type.version publishedVersion

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication